Reprint of “Supervised sentiment analysis in Czech social media”
作者：
Highlights：
• We explore state-of-the-art supervised machine learning methods for sentiment analysis of Czech social media.
• We provide a large human-annotated Czech social media corpus.
• We explore different pre-processing techniques and employ various features and classifiers.
• We experiment with five different feature selection algorithms.
• Results are also reported on other widely popular domains, such as movie and product reviews.
摘要
•We explore state-of-the-art supervised machine learning methods for sentiment analysis of Czech social media.•We provide a large human-annotated Czech social media corpus.•We explore different pre-processing techniques and employ various features and classifiers.•We experiment with five different feature selection algorithms.•Results are also reported on other widely popular domains, such as movie and product reviews.
论文关键词：Sentiment analysis,Czech language,Social media,Machine learning,Feature selection
论文评审过程：Received 12 August 2013, Revised 20 December 2013, Accepted 7 May 2014, Available online 29 May 2015, Version of Record 6 June 2015.
论文官网地址：https://doi.org/10.1016/j.ipm.2015.05.006
